Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8083
    Prev
    Next
    INDEX
    Explanations

    SiriusXM NFL Radio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     polizia
    -0.74
    othek
    -0.72
     yelled
    -0.72
     Hadd
    -0.71
    enegro
    -0.70
    enumerable
    -0.70
    Boton
    -0.70
     CW
    -0.69
     ی
    -0.69
     redress
    -0.69
    POSITIVE LOGITS
     satellite
    1.71
     Satellite
    1.39
    satellite
    1.38
     Sirius
    1.29
    Satellite
    1.23
    Sirius
    1.16
    衛
    1.14
     XM
    1.09
    XM
    1.05
    卫星
    0.98
    Activations Density 0.022%

    No Known Activations